{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LEJLBWEN2DVHGXYDGSDTUVUIBV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"cc5ea8dfda16a330252507431628951162e15b396dc356155dcb8bf528c6aa06","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-30T16:52:30Z","title_canon_sha256":"6406987ec8f85f208bbf00212684fc8b7571dec7e1eb9de9260973e14d9539a6"},"schema_version":"1.0","source":{"id":"2205.15237","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.15237","created_at":"2026-07-05T04:27:25Z"},{"alias_kind":"arxiv_version","alias_value":"2205.15237v1","created_at":"2026-07-05T04:27:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15237","created_at":"2026-07-05T04:27:25Z"},{"alias_kind":"pith_short_12","alias_value":"LEJLBWEN2DVH","created_at":"2026-07-05T04:27:25Z"},{"alias_kind":"pith_short_16","alias_value":"LEJLBWEN2DVHGXYD","created_at":"2026-07-05T04:27:25Z"},{"alias_kind":"pith_short_8","alias_value":"LEJLBWEN","created_at":"2026-07-05T04:27:25Z"}],"graph_snapshots":[{"event_id":"sha256:af1b2f41219851456fc693a76034481dd735012094a8b63b98548f3ab3dcda81","target":"graph","created_at":"2026-07-05T04:27:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2205.15237/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in vision-language pre-training (VLP) have demonstrated impressive performance in a range of vision-language (VL) tasks. However, there exist several challenges for measuring the community's progress in building general multi-modal intelligence. First, most of the downstream VL datasets are annotated using raw images that are already seen during pre-training, which may result in an overestimation of current VLP models' generalization ability. Second, recent VLP work mainly focuses on absolute performance but overlooks the efficiency-performance trade-off, which is also an impor","authors_text":"Shizhe Diao, Wangchunshu Zhou, Xinsong Zhang, Yan Zeng","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-30T16:52:30Z","title":"VLUE: A Multi-Task Benchmark for Evaluating Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15237","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b2d128fb7f5e4f44a1d30f79416e8ad41604385fafc6f68f392998e84671a970","target":"record","created_at":"2026-07-05T04:27:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"cc5ea8dfda16a330252507431628951162e15b396dc356155dcb8bf528c6aa06","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-30T16:52:30Z","title_canon_sha256":"6406987ec8f85f208bbf00212684fc8b7571dec7e1eb9de9260973e14d9539a6"},"schema_version":"1.0","source":{"id":"2205.15237","kind":"arxiv","version":1}},"canonical_sha256":"5912b0d88dd0ea735f0334873a56880d46fa43b4dfff6cb58d37661a36683322","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5912b0d88dd0ea735f0334873a56880d46fa43b4dfff6cb58d37661a36683322","first_computed_at":"2026-07-05T04:27:25.956658Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:27:25.956658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H9ZtGUH63gQ3JCeuazkhe5rMhs1gA8FqpIr2wEjbfU3hA35krI79Pg2HfCj5ZYmdobE1eq7L1H46X2S7mOxiBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:27:25.957106Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.15237","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2d128fb7f5e4f44a1d30f79416e8ad41604385fafc6f68f392998e84671a970","sha256:af1b2f41219851456fc693a76034481dd735012094a8b63b98548f3ab3dcda81"],"state_sha256":"a57b01e38fb526bb7b06af9744f01abbe65d90140696ded29b978c0bca9e9eb6"}